Muutke küpsiste eelistusi

E-raamat: Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science 2e 2nd Edition [Wiley Online]

(University of Lausanne, Switzerland), (Edinburgh University), (Lausanne University, Switzerland), (IUAV University, Venice, Italy), (Universita di Venezia)
  • Formaat: 480 pages
  • Sari: Statistics in Practice
  • Ilmumisaeg: 05-Sep-2014
  • Kirjastus: John Wiley & Sons Inc
  • ISBN-10: 1118914767
  • ISBN-13: 9781118914762
Teised raamatud teemal:
  • Wiley Online
  • Hind: 109,96 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science 2e 2nd EditionSuurem pilt
  • Formaat: 480 pages
  • Sari: Statistics in Practice
  • Ilmumisaeg: 05-Sep-2014
  • Kirjastus: John Wiley & Sons Inc
  • ISBN-10: 1118914767
  • ISBN-13: 9781118914762
Teised raamatud teemal:
Wiley Online e-raamatudRohkem infot Wiley Online kohta
Raamatu kodulehekülg: https://onlinelibrary.wiley.com/doi/book/10.1002/9781118914762
Bayesian Networks This book should have a place on the bookshelf of every forensic scientist who cares about the science of evidence interpretation. Dr. Ian Evett, Principal Forensic Services Ltd, London, UK

Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science

Second Edition

Continuing developments in science and technology mean that the amounts of information forensic scientists are able to provide for criminal investigations is ever increasing. The commensurate increase in complexity creates diffculties for scientists and lawyers with regard to evaluation and interpretation, notably with respect to issues of inference and decision. Probability theory, implemented through graphical methods, and specifically Bayesian networks, provides powerful methods to deal with this complexity. Extensions of these methods to elements of decision theory provide further support and assistance to the judicial system.

Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science provides a unique and comprehensive introduction to the use of Bayesian decision networks for the evaluation and interpretation of scientific findings in forensic science, and for the support of decision-makers in their scientific and legal tasks.







Includes self-contained introductions to probability and decision theory. Develops the characteristics of Bayesian networks, object-oriented Bayesian networks and their extension to decision models. Features implementation of the methodology with reference to commercial and academically available software. Presents standard networks and their extensions that can be easily implemented and that can assist in the readers own analysis of real cases. Provides a technique for structuring problems and organizing data based on methods and principles of scientific reasoning. Contains a method for the construction of coherent and defensible arguments for the analysis and evaluation of scientific findings and for decisions based on them. Is written in a lucid style, suitable for forensic scientists and lawyers with minimal mathematical background. Includes a foreword by Ian Evett.

The clear and accessible style of this second edition makes this book ideal for all forensic scientists, applied statisticians and graduate students wishing to evaluate forensic findings from the perspective of probability and decision analysis. It will also appeal to lawyers and other scientists and professionals interested in the evaluation and interpretation of forensic findings, including decision making based on scientific information.
Foreword xiii
Preface to the second edition xvii
Preface to the first edition xxi
1 The logic of decision
1(44)
1.1 Uncertainty and probability
1(11)
1.1.1 Probability is not about numbers, it is about coherent reasoning under uncertainty
1(1)
1.1.2 The first two laws of probability
2(1)
1.1.3 Relevance and independence
3(2)
1.1.4 The third law of probability
5(1)
1.1.5 Extension of the conversation
6(1)
1.1.6 Bayes' theorem
6(1)
1.1.7 Probability trees
7(2)
1.1.8 Likelihood and probability
9(1)
1.1.9 The calculus of (probable) truths
10(2)
1.2 Reasoning under uncertainty
12(7)
1.2.1 The Hound of the Baskervilles
12(1)
1.2.2 Combination of background information and evidence
13(2)
1.2.3 The odds form of Bayes' theorem
15(1)
1.2.4 Combination of evidence
16(1)
1.2.5 Reasoning with total evidence
16(2)
1.2.6 Reasoning with uncertain evidence
18(1)
1.3 Population proportions, probabilities and induction
19(9)
1.3.1 The statistical syllogism
19(2)
1.3.2 Expectations and population proportions
21(1)
1.3.3 Probabilistic explanations
22(3)
1.3.4 Abduction and inference to the best explanation
25(1)
1.3.5 Induction the Bayesian way
26(2)
1.4 Decision making under uncertainty
28(14)
1.4.1 Bookmakers in the Courtrooms?
28(1)
1.4.2 Utility theory
29(4)
1.4.3 The rule of maximizing expected utility
33(1)
1.4.4 The loss function
34(1)
1.4.5 Decision trees
35(3)
1.4.6 The expected value of information
38(4)
1.5 Further readings
42(3)
2 The logic of Bayesian networks and influence diagrams
45(40)
2.1 Reasoning with graphical models
45(20)
2.1.1 Beyond detective stories
45(1)
2.1.2 Bayesian networks
46(2)
2.1.3 A graphical model for relevance
48(2)
2.1.4 Conditional independence
50(1)
2.1.5 Graphical models for conditional independence: d-separation
51(2)
2.1.6 A decision rule for conditional independence
53(1)
2.1.7 Networks for evidential reasoning
53(3)
2.1.8 The Markov property
56(2)
2.1.9 Influence diagrams
58(2)
2.1.10 Conditional independence in influence diagrams
60(1)
2.1.11 Relevance and causality
61(2)
2.1.12 The Hound of the Baskervilles revisited
63(2)
2.2 Reasoning with Bayesian networks and influence diagrams
65(17)
2.2.1 Divide and conquer
66(1)
2.2.2 From directed to triangulated graphs
67(2)
2.2.3 From triangulated graphs to junction trees
69(2)
2.2.4 Solving influence diagrams
71(3)
2.2.5 Object-oriented Bayesian networks
74(5)
2.2.6 Solving object-oriented Bayesian networks
79(3)
2.3 Further readings
82(3)
2.3.1 General
82(1)
2.3.2 Bayesian networks and their predecessors in judicial contexts
83(2)
3 Evaluation of scientific findings in forensic science
85(28)
3.1 Introduction
85(1)
3.2 The value of scientific findings
86(4)
3.3 Principles of forensic evaluation and relevant propositions
90(10)
3.3.1 Source level propositions
92(2)
3.3.2 Activity level propositions
94(3)
3.3.3 Crime level propositions
97(3)
3.4 Pre-assessment of the case
100(3)
3.5 Evaluation using graphical models
103(10)
3.5.1 Introduction
103(1)
3.5.2 General aspects of the construction of Bayesian networks
103(2)
3.5.3 Eliciting structural relationships
105(1)
3.5.4 Level of detail of variables and quantification of influences
106(2)
3.5.5 Deriving an alternative network structure
108(5)
4 Evaluation given source level propositions
113(16)
4.1 General considerations
113(2)
4.2 Standard statistical distributions
115(2)
4.3 Two stains, no putative source
117(5)
4.3.1 Likelihood ratio for source inference when no putative source is available
117(2)
4.3.2 Bayesian network for a two-trace case with no putative source
119(2)
4.3.3 An alternative network structure for a two trace no putative source case
121(1)
4.4 Multiple propositions
122(7)
4.4.1 Form of the likelihood ratio
122(1)
4.4.2 Bayesian networks for evaluation given multiple propositions
123(6)
5 Evaluation given activity level propositions
129(30)
5.1 Evaluation of transfer material given activity level propositions assuming a direct source relationship
130(20)
5.1.1 Preliminaries
130(1)
5.1.2 Derivation of a basic structure for a Bayesian network
131(3)
5.1.3 Modifying the basic network
134(3)
5.1.4 Further considerations about background presence
137(2)
5.1.5 Background from different sources
139(3)
5.1.6 An alternative description of the findings
142(3)
5.1.7 Bayesian network for an alternative description of findings
145(2)
5.1.8 Increasing the level of detail of selected propositions
147(2)
5.1.9 Evaluation of the proposed model
149(1)
5.2 Cross- or two-way transfer of trace material
150(4)
5.3 Evaluation of transfer material given activity level propositions with uncertainty about the true source
154(5)
5.3.1 Network structure
154(1)
5.3.2 Evaluation of the network
154(3)
5.3.3 Effect of varying assumptions about key factors
157(2)
6 Evaluation given crime level propositions
159(37)
6.1 Material found on a crime scene: A general approach
159(9)
6.1.1 Generic network construction for single offender
159(2)
6.1.2 Evaluation of the network
161(2)
6.1.3 Extending the single-offender scenario
163(3)
6.1.4 Multiple offenders
166(2)
6.1.5 The role of the relevant population
168(1)
6.2 Findings with more than one component: The example of marks
168(14)
6.2.1 General considerations
168(1)
6.2.2 Adding further propositions
169(1)
6.2.3 Derivation of the likelihood ratio
170(2)
6.2.4 Consideration of distinct components
172(5)
6.2.5 An extension to firearm examinations
177(4)
6.2.6 A note on the likelihood ratio
181(1)
6.3 Scenarios with more than one trace: `Two stain-one offender' cases
182(3)
6.4 Material found on a person of interest
185(11)
6.4.1 General form
185(2)
6.4.2 Extending the numerator
187(2)
6.4.3 Extending the denominator
189(1)
6.4.4 Extended form of the likelihood ratio
190(1)
6.4.5 Network construction and examples
190(6)
7 Evaluation of DNA profiling results
196(53)
7.1 DNA likelihood ratio
196(2)
7.2 Network approaches to the DNA likelihood ratio
198(5)
7.2.1 The `match' approach
198(1)
7.2.2 Representation of individual alleles
198(4)
7.2.3 Alternative representation of a genotype
202(1)
7.3 Missing suspect
203(3)
7.4 Analysis when the alternative proposition is that a brother of the suspect left the crime stain
206(8)
7.4.1 Revision of probabilities and networks
206(6)
7.4.2 Further considerations on conditional genotype probabilities
212(2)
7.5 Interpretation with more than two propositions
214(3)
7.6 Evaluation with more than two propositions
217(3)
7.7 Partially corresponding profiles
220(3)
7.8 Mixtures
223(4)
7.8.1 Considering multiple crime stain contributors
223(2)
7.8.2 Bayesian network for a three-allele mixture scenario
225(2)
7.9 Kinship analyses
227(7)
7.9.1 A disputed paternity
227(3)
7.9.2 An extended paternity scenario
230(2)
7.9.3 A case of questioned maternity
232(2)
7.10 Database search
234(7)
7.10.1 Likelihood ratio after database searching
234(3)
7.10.2 An analysis focussing on posterior probabilities
237(4)
7.11 Probabilistic approaches to laboratory error
241(5)
7.11.1 Implicit approach to typing error
241(2)
7.11.2 Explicit approach to typing error
243(3)
7.12 Further reading
246(3)
7.12.1 A note on object-oriented Bayesian networks
246(1)
7.12.2 Additional topics
246(3)
8 Aspects of combining evidence
249(32)
8.1 Introduction
249(1)
8.2 A difficulty in combining evidence: The `problem of conjunction'
250(2)
8.3 Generic patterns of inference in combining evidence
252(10)
8.3.1 Preliminaries
252(1)
8.3.2 Dissonant evidence: Contradiction and conflict
252(4)
8.3.3 Harmonious evidence: Corroboration and convergence
256(5)
8.3.4 Drag coefficient
261(1)
8.4 Examples of the combination of distinct items of evidence
262(19)
8.4.1 Handwriting and fingermarks
262(4)
8.4.2 Issues in DNA analyses
266(1)
8.4.3 One offender and two corresponding traces
267(4)
8.4.4 Firearms and gunshot residues
271(8)
8.4.5 Comments
279(2)
9 Networks for continuous models
281(33)
9.1 Random variables and distribution functions
281(8)
9.1.1 Normal distribution
283(4)
9.1.2 Bivariate Normal distribution
287(1)
9.1.3 Conditional expectation and variance
288(1)
9.2 Samples and estimates
289(3)
9.2.1 Summary statistics
289(2)
9.2.2 The Bayesian paradigm
291(1)
9.3 Continuous Bayesian networks
292(14)
9.3.1 Propagation in a continuous Bayesian network
295(5)
9.3.2 Background data
300(2)
9.3.3 Intervals for a continuous entity
302(4)
9.4 Mixed networks
306(8)
9.4.1 Bayesian network for a continuous variable with a discrete parent
308(2)
9.4.2 Bayesian network for a continuous variable with a continuous parent and a binary parent, unmarried
310(4)
10 Pre-assessment
314(29)
10.1 Introduction
314(1)
10.2 General elements of pre-assessment
315(1)
10.3 Pre-assessment in a fibre case: A worked through example
316(5)
10.3.1 Preliminaries
316(1)
10.3.2 Propositions and relevant events
317(2)
10.3.3 Expected likelihood ratios
319(2)
10.3.4 Construction of a Bayesian network
321(1)
10.4 Pre-assessment in a cross-transfer scenario
321(7)
10.4.1 Bidirectional transfer
321(3)
10.4.2 A Bayesian network for a pre-assessment of a cross-transfer scenario
324(1)
10.4.3 The value of the findings
325(3)
10.5 Pre-assessment for consignment inspection
328(7)
10.5.1 Inspecting small consignments
328(2)
10.5.2 Bayesian network for inference about small consignments
330(3)
10.5.3 Pre-assessment for inspection of small consignments
333(2)
10.6 Pre-assessment for gunshot residue particles
335(8)
10.6.1 Formation and deposition of gunshot residue particles
335(1)
10.6.2 Bayesian network for grouped expected findings (GSR counts)
336(3)
10.6.3 Examples for GSR count pre-assessment using a Bayesian network
339(4)
11 Bayesian decision networks
343(27)
11.1 Decision making in forensic science
343(1)
11.2 Examples of forensic decision analyses
344(24)
11.2.1 Deciding about whether or not to perform a DNA analysis
344(8)
11.2.2 Probability assignment as a question of decision making
352(5)
11.2.3 Decision analysis for consignment inspection
357(9)
11.2.4 Decision after database searching
366(2)
11.3 Further readings
368(2)
12 Object-oriented networks
370(18)
12.1 Object orientation
370(1)
12.2 General elements of object-oriented networks
371(7)
12.2.1 Static versus dynamic networks
371(2)
12.2.2 Dynamic Bayesian networks as object-oriented networks
373(1)
12.2.3 Refining internal class descriptions
374(4)
12.3 Object-oriented networks for evaluating DNA profiling results
378(10)
12.3.1 Basic disputed paternity case
378(1)
12.3.2 Useful class networks for modelling kinship analyses
379(2)
12.3.3 Object-oriented networks for kinship analyses
381(2)
12.3.4 Object-oriented networks for inference of source
383(2)
12.3.5 Refining internal class descriptions and further considerations
385(3)
13 Qualitative, sensitivity and conflict analyses
388(31)
13.1 Qualitative probability models
389(13)
13.1.1 Qualitative influence
389(3)
13.1.2 Additive synergy
392(2)
13.1.3 Product synergy
394(2)
13.1.4 Properties of qualitative relationships
396(5)
13.1.5 Implications of qualitative graphical models
401(1)
13.2 Sensitivity analyses
402(8)
13.2.1 Preliminaries
402(1)
13.2.2 Sensitivity to a single probability assignment
403(2)
13.2.3 Sensitivity to two probability assignments
405(3)
13.2.4 Sensitivity to prior distribution
408(2)
13.3 Conflict analysis
410(9)
13.3.1 Conflict detection
411(3)
13.3.2 Tracing a conflict
414(1)
13.3.3 Conflict resolution
415(4)
References 419(14)
Author index 433(5)
Subject index 438
FRANCO TARONI, University of Lausanne, Switzerland

ALEX BIEDERMANN, University of Lausanne, Switzerland

SILVIA BOZZA, University Ca Foscari of Venice, Italy

PAOLO GARBOLINO, University IUAV of Venice, Italy

COLIN AITKEN, University ofEdinburgh, UK
Püsilink: https://www.kriso.ee/db/9781118914762_pe.html
Ei ole sisse logitud.